基于光谱图像的森林病虫害自动检测方法  

Automatic detection method of forest diseases and insect pests based on spectral images

作　　者：周晓丽 周立君[2] 伊力塔 刘宇[2] ZHOU Xiaoli;ZHOU Lijun;YI Lita;LIU Yu(Forest and Grassland Protection and Development Center of Ar Horqin Banner,Ar Horqin Banner 025550,China;Xi'an Institute of Applied Optics,Xi'an 710065,China)

机构地区：[1]阿鲁科尔沁旗森林草原保护发展中心,内蒙古阿鲁科尔沁旗025550 [2]西安应用光学研究所,陕西西安710065

出　　处：《应用光学》2023年第2期420-426,共7页Journal of Applied Optics

基　　金：兵器联合基金(6141B01020205)。

摘　　要：我国天然林区分布范围广,地形复杂,依靠传统的护林员巡检方式进行林木病虫害防治,效率较低,难于及时发现早期的林木病虫害,可能因此错过防治的最佳时机。针对该问题,设计了一种基于多光谱图像检测林木病虫害的深度学习网络,研发了一套检测软件,通过无人机挂飞实验,利用搭建的深度学习网络,完成林区染病区检测,对检测结果进行了分析。The natural forest areas in China are widely distributed and the terrain is complex. Relying on the traditional patrol detection method of forest rangers to prevent and control forest diseases and insect pests is inefficient, so it is difficult to find early forest diseases and insect pests in time, which may miss the best time for prevention and control. In view of this problem, a deep learning network based on multispectral image detection of forest diseases and insect pests was designed, and a set of detection software was developed.Through the UAV hanging flight experiment, the built deep learning network was used to complete the detection of infected areas in forest areas, and the detection results were analyzed.

关 键 词：光谱图像 森林病虫害 深度学习 注意力机制 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]